CN114144648A - Sensing device and sensing device system - Google Patents

Abstract

A sensor device (100) comprises: a plurality of sensor units (14) which have a magnetic sensor (15) as an element arranged in one of the 1 st structural body and the 2 nd structural body and a magnet (16) as an element arranged in the other of the 1 st structural body and the 2 nd structural body, and which detect a change in the relative position of the magnetic sensor (15) and the magnet (16) based on a change in magnetic flux detected by the magnetic sensor (15); a calculation unit (25) that obtains measurement results relating to at least 1 of the amount of movement of the 1 st structure relative to the 2 nd structure, the amount of rotation of the 1 st structure relative to the 2 nd structure, and the external force applied to the 1 st structure, by calculation based on the detection results of the plurality of sensor units (14); and a determination unit (26) that determines, based on the detection results of the plurality of sensor units (14), whether or not there is an abnormality that causes a change in magnetic flux due to a factor other than a change in the relative position of the magnetic sensor (15) and the magnet (16).

Description

Sensing device and sensing device system

Technical Field

The present invention relates to a sensor device and a sensor device system for detecting movement of a structure due to an external force applied to the structure.

Background

Conventionally, there is known a sensor device which has a combination of a plurality of magnetic sensors for detecting magnetic fluxes and a magnet and detects movement in each direction of the 3-axis or force acting in each direction of the 3-axis. Patent document 1 discloses a force sensor that is provided with a combination of a plurality of magnets and hall elements, which are magnetic sensors, and detects forces acting in various directions by detecting relative positions of the magnets and the hall elements.

Patent document 1: japanese laid-open patent publication No. Sho 60-177232

Disclosure of Invention

As in the force sensor disclosed in patent document 1, a conventional sensor device having a magnetic sensor is affected by a magnetic field existing outside the sensor device, and thus a detection result changes. The conventional sensor device cannot confirm the occurrence of an abnormality even if the detection result changes due to a factor other than a change in the relative position of the magnet and the magnetic sensor, and therefore outputs the detection result as in the case of normal detection. As described above, the conventional sensor device has a problem that it is impossible to confirm the occurrence of an abnormality at the time of detection.

The present invention has been made in view of the above circumstances, and an object thereof is to obtain a sensor device capable of confirming occurrence of an abnormality at the time of detection.

In order to solve the above-described problems and achieve the object, a sensor device according to the present invention detects movement of an operating body that moves when an external force is applied. The sensing device according to the present invention includes: 1 st structure which is an operation body; and a 2 nd structure other than the operation body. The sensing device according to the present invention includes: a plurality of sensor units each including a magnetic sensor as an element arranged in one of the 1 st and 2 nd structures and a magnet as an element arranged in the other of the 1 st and 2 nd structures, and detecting a change in relative position between the magnetic sensor and the magnet based on a change in magnetic flux detected by the magnetic sensor; and a calculation unit that calculates measurement results regarding at least 1 of the movement amount of the 1 st structure relative to the 2 nd structure, the rotation amount of the 1 st structure relative to the 2 nd structure, and the external force applied to the 1 st structure, by calculation based on the detection results of the plurality of sensor units. The sensor device according to the present invention includes a determination unit that determines whether or not there is an abnormality in a magnetic flux change due to a factor other than a change in the relative position of the magnetic sensor and the magnet, based on the detection results of the plurality of sensor units.

ADVANTAGEOUS EFFECTS OF INVENTION

The sensing device according to the present invention has an effect of being able to confirm the occurrence of an abnormality at the time of detection.

Drawings

Fig. 1 is a 1 st sectional view showing a sensor device according to embodiment 1 of the present invention.

Fig. 2 is a 2 nd sectional view showing a sensor device according to embodiment 1.

Fig. 3 is a diagram showing a functional configuration of the sensor device according to embodiment 1.

Fig. 4 is a view 1 illustrating a positional relationship between the magnetic sensor and the magnet in the cross section shown in fig. 2.

Fig. 5 is a view 2 illustrating a positional relationship between the magnetic sensor and the magnet in the cross section shown in fig. 2.

Fig. 6 is a flowchart for explaining the operation of the sensor device according to embodiment 1.

Fig. 7 is a diagram 1 showing an example of the hardware configuration of the measurement apparatus according to embodiment 1.

Fig. 8 is a diagram 2 showing an example of the hardware configuration of the measurement device according to embodiment 1.

Fig. 9 is a diagram illustrating a modification of embodiment 1.

Fig. 10 is a flowchart for explaining the operation of the sensor device according to embodiment 2 of the present invention.

Fig. 11 is a diagram showing a functional configuration of a sensor device according to embodiment 3 of the present invention.

Fig. 12 is a diagram showing a functional configuration of a sensor device according to embodiment 4 of the present invention.

Fig. 13 is a diagram showing an example of a sensing device that performs both learning in embodiment 3 and learning in embodiment 4.

Fig. 14 is a diagram showing an example of the configuration of the neural network used for learning in embodiments 3 and 4.

Detailed Description

A sensor device and a sensor device system according to an embodiment of the present invention will be described in detail below with reference to the drawings. The present invention is not limited to the embodiments.

Embodiment 1.

Fig. 1 is a 1 st sectional view showing a sensor device according to embodiment 1 of the present invention. Fig. 2 is a 2 nd cross-sectional view showing a sensor device according to embodiment 1 of the present invention. The section shown in fig. 1 is a longitudinal section of the sensing apparatus 100 and is a section at the line I-I shown in fig. 2. The cross-section shown in fig. 2 is a cross-section of the sensing device 100 and is a cross-section at line II-II shown in fig. 1.

The sensor device 100 detects movement of an operation body that moves by receiving an external force. The sensor device 100 detects movement of the operating body in each direction of the 3 axes and rotation of the operating body around each of the 3 axes.

The sensor device 100 has the 1 st structure 11 as an operating body and the 2 nd structure 12 as a structure other than the operating body. Both the 1 st structure 11 and the 2 nd structure 12 are rigid bodies. The state of the sensing device 100 when the 1 st structure 11 is not subjected to an external force may be referred to as a reference state. The central axis N is an axis perpendicular to the cross section shown in fig. 2, and represents the center of the 2 nd structure 12. In the reference state, the center of the 1 st structure 11 is located on the central axis N.

The elastic body 13 connects the 1 st structure 11 and the 2 nd structure 12. An object such as a spring or rubber is used for the elastic body 13. The 1 st structure 11 and the 2 nd structure 12 are coupled to each other via the elastic body 13, whereby the 1 st structure 11 is supported by the 2 nd structure 12 in a state in which the translational operation and the rotational operation are possible with respect to the 2 nd structure 12.

The 1 st structure 11 is moved from the position in the reference state by performing a translational motion in response to an external force. The 1 st structure 11 moves in the direction of the applied external force. The 1 st structure 11 moves by a distance corresponding to the magnitude of the received external force. If the external force is not applied, the elastic body 13 returns to the position in the reference state by the restoring force. Further, the 1 st structure 11 receives an external force and performs a rotational operation, whereby the posture changes from the reference state. When the external force is not applied, the 1 st structure 11 is restored to the posture in the reference state by the restoring force of the elastic body 13.

The sensing device 100 has 3 sensor units 14a, 14b, 14 c. The sensor unit 14a has a magnetic sensor 15a and a magnet 16 a. The sensor unit 14b includes a magnetic sensor 15b and a magnet 16 b. The sensor unit 14c has a magnetic sensor 15c and a magnet 16 c. The magnetic sensors 15a, 15b, and 15c are elements attached to the 1 st structure 11. The magnets 16a, 16b, and 16c are elements attached to the 2 nd structure 12. The sensor units 14a, 14b, and 14c are referred to as the sensor units 14 without being distinguished from each other. The magnetic sensors 15a, 15b, and 15c are referred to as magnetic sensors 15 without distinction. The magnets 16a, 16b, and 16c are referred to as magnets 16 without distinction.

The magnetic sensor 15 is configured to be able to detect magnetic fluxes in each direction of the 3-axis. The magnetic sensor 15 is an integrated circuit capable of detecting magnetic fluxes in each direction of the 3-axis. The magnetic sensor 15 may be a combination of 3 hall elements each capable of detecting a magnetic flux in the 1-axis direction. The magnet 16 is a permanent magnet or an electromagnet.

The magnetic sensors 15a, 15b, and 15c are provided on the outer edge of the 1 st structure 11. In the cross section shown in fig. 2, the magnetic sensors 15a, 15b, and 15c are arranged at equal intervals on the outer edge of the 1 st structure 11. The magnet 16a is disposed at a position facing the magnetic sensor 15 a. The magnetic sensor 15a is disposed in the magnetic field formed by the magnet 16 a. The magnet 16b is disposed at a position facing the magnetic sensor 15 b. The magnetic sensor 15b is disposed in the magnetic field formed by the magnet 16 b. The magnet 16c is disposed at a position facing the magnetic sensor 15 c. The magnetic sensor 15c is disposed in the magnetic field formed by the magnet 16 c.

The magnetic sensor 15 outputs values of magnetic fluxes in the 3-axis directions. In the sensor unit 14, the relative position of the magnetic sensor 15 and the magnet 16 changes, and the value of the magnetic flux detected by the magnetic sensor 15 changes accordingly. The sensor unit 14 functions as a 3-dimensional position sensor. The sensor apparatus 100 has 3 sensor units 14a, 14b, 14c, thereby detecting a change in position at 3 points of the 1 st structure 11. The sensor device 100 detects the movement of the 1 st structure 11 in each direction of the 3 axes and the rotation of the 1 st structure 11 around each of the 3 axes by using the position information on each of the 3 points.

The sensor device 100 is installed by fixing the 2 nd structure 12 to an installation site. The sensor device 100 measures the displacement amount of the 1 st structure 11 generated by the operator moving the 1 st structure 11. The sensor device 100 measures the total displacement amount in the 6 direction of the translational motion in the 3 direction and the rotational motion in the 3 direction. The sensor device 100 can be used as an input device for causing the robot to perform the same operation as the 1 st structure 11.

The sensing device 100 can measure the magnitude of the external force applied to the 1 st structure 11 by converting the displacement amount of the 1 st structure 11 into the magnitude of the force. The sensing device 100 measures the magnitude of the external force in the 6 direction in total of the translational motion in the 3 direction and the rotational motion in the 3 direction. By measuring the amount of displacement corresponding to the magnitude of the force applied to the 1 st structure 11, a conversion rule indicating the relationship between the magnitude of the force and the amount of displacement is obtained. The sensing apparatus 100 converts the amount of displacement to the magnitude of force based on a conversion rule obtained in advance. As described above, the sensor device 100 can also be used as a force sensor.

The shape of the 1 st structure 11 and the shape of the 2 nd structure 12 are not limited to those shown in fig. 1 and 2, and may be any shape. The magnetic sensors 15a, 15b, and 15c may be mounted on the 2 nd structure 12 without being mounted on the 1 st structure 11. In this case, the magnets 16a, 16b, and 16c are attached to the 1 st structure 11 without being attached to the 2 nd structure 12. The sensor unit 14a may be configured such that the magnetic sensor 15a is disposed in one of the 1 st structure 11 and the 2 nd structure 12, and the magnet 16a is disposed in the other of the 1 st structure 11 and the 2 nd structure 12. The sensor unit 14b may be configured such that the magnetic sensor 15b is disposed in one of the 1 st structure 11 and the 2 nd structure 12, and the magnet 16b is disposed in the other of the 1 st structure 11 and the 2 nd structure 12. In the sensor unit 14c, the magnetic sensor 15c may be disposed in one of the 1 st structure 11 and the 2 nd structure 12, and the magnet 16c may be disposed in the other of the 1 st structure 11 and the 2 nd structure 12.

Fig. 3 is a diagram showing a functional configuration of the sensor device according to embodiment 1. The sensor device 100 has an evaluation device 20. The measuring device 20 measures the distance the 1 st structure 11 moves relative to the 2 nd structure 12 and the amount of rotation of the 1 st structure 11 relative to the 2 nd structure 12. In fig. 1 and 2, the measuring device 20 is not shown.

The magnetic sensor 15 outputs data, which is a detection result of the magnetic flux value, to the measurement device 20. The measurement device 20 includes: an acquisition unit 21 that acquires data output from the magnetic sensor 15; a control unit 22 for controlling the measurement device 20; a storage unit 23 that stores information; and an output unit 24 that outputs information.

The control unit 22 includes an arithmetic unit 25 that performs arithmetic processing of the data acquired by the acquisition unit 21. The calculation unit 25 calculates a measurement result related to the movement amount of the 1 st structure 11 relative to the 2 nd structure 12 by calculation based on the detection results of the sensor units 14a, 14b, and 14 c. The calculation unit 25 calculates the measurement result related to the rotation amount of the 1 st structure 11 relative to the 2 nd structure 12 by calculation based on the detection results of the sensor units 14a, 14b, and 14 c. The calculation unit 25 may convert the displacement amount of the 1 st structure 11 into the magnitude of the force to obtain the measurement result related to the external force applied to the 1 st structure 11. That is, the calculation unit 25 obtains measurement results regarding at least 1 of the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, and the external force applied to the 1 st structure 11 by calculation based on the detection results of the plurality of sensor units 14.

The control unit 22 has a determination unit 26, and the determination unit 26 determines whether there is an abnormality based on the detection results of the sensor units 14a, 14b, and 14 c. The abnormality is a state in which the operation of the 1 st structure 11 cannot be normally detected, and is a state in which the magnetic flux changes due to factors other than a change in the relative position of the magnetic sensor 15 and the magnet 16. In embodiment 1, the determination unit 26 determines the presence or absence of an abnormality based on the result of determining the distances between the magnets 16a, 16b, and 16c, which are the elements arranged in the 2 nd structure 12.

The storage unit 23 stores the measurement result obtained by the calculation performed by the calculation unit 25. The storage unit 23 stores various parameters used for the calculation by the calculation unit 25 and various parameters used for the determination by the determination unit 26. The output unit 24 outputs the measurement result. The output unit 24 outputs an alarm when the determination unit 26 determines that there is an abnormality. The output unit 24 outputs an alarm signal to an external device. Alternatively, the output unit 24 may output an alarm by an alarm sound generated by an audio device or an alarm display of a display device.

Next, calculation of the measurement result by the calculation unit 25 will be described. The calculation unit 25 converts the detection results of the magnetic flux values obtained by the magnetic sensors 15a, 15b, and 15c into displacement data indicating a displacement with 6 degrees of freedom. The displacement of 6 degrees of freedom is a displacement of a translational motion in each direction of the 3 axes and a displacement of a rotational motion centered on each of the 3 axes. In the following description, the detection results of the values of the magnetic fluxes obtained by the magnetic sensors 15a, 15b, and 15c are sometimes referred to as magnetic data.

The vector G representing the displacement with 6 degrees of freedom of the 1 st structure 11 is defined by the following formula (1). Here, "X" represents a translational motion in the direction of the 1 st axis among the 3 axes. "Y" represents a translational motion in the direction of the 2 nd axis among the 3 axes. "Z" represents the 3 rd axis among the 3 axesAnd (4) translational motion of direction. "a" indicates a rotation motion in the 1 st rotation direction among the 3 rotation directions. "B" indicates a rotation motion in the 2 nd rotation direction among the 3 rotation directions. "C" indicates a rotation motion in the 3 rd rotation direction among the 3 rotation directions. In the formula (1), "G.di-R^6×1"indicates that vector G is formed by elements of 6 rows and 1 columns made of real numbers.

[ formula 1 ]

G＝(X，Y，Z，A，B，C)∈R^6×1…(1)

The magnetic data obtained by the magnetic sensor 15a is set to "M₁"the magnetic data obtained by the magnetic sensor 15b is set to" M₂And the magnetic data obtained by the magnetic sensor 15c is set to "M₃”，“M_n"(n-1, 2, 3) is represented by the following formula (2).

[ formula 2 ]

M_n＝(x_n，y_n，z_n)_{n＝1，2，3}∈R^3×1…(2)

Further, "x₁"indicates the value of the magnetic flux in the 1 st axis direction detected by the magnetic sensor 15 a. "y" is₁"indicates the value of the magnetic flux in the 2 nd axis direction detected by the magnetic sensor 15 a. "z" is₁"indicates the value of the magnetic flux in the 3 rd axis direction detected by the magnetic sensor 15 a. "x₂"indicates the value of the magnetic flux in the 1 st axis direction detected by the magnetic sensor 15 b. "y" is₂"indicates the value of the magnetic flux in the 2 nd axis direction detected by the magnetic sensor 15 b. "z" is₂"indicates the value of the magnetic flux in the 3 rd axis direction detected by the magnetic sensor 15 b. "x₃"indicates the value of the magnetic flux in the 1 st axis direction detected by the magnetic sensor 15 c. "y" is₃"indicates the value of the magnetic flux in the 2 nd axis direction detected by the magnetic sensor 15 c. "z" is₃"indicates the value of the magnetic flux in the 3 rd axis direction detected by the magnetic sensor 15 c. (x)₁，y₁，z₁) Is as magnetic data "M₁"3 values. (x)₂，y₂，z₂) Is as magnetic data "M₂"3 values. (x)₃，y₃，z₃) Is as magnetic data "M₃"3 values.

When 9 values are to be used, i.e. magnetic data "M₁”、“M₂"and" M₃"the matrix transformed into the displacement of 6 degrees of freedom is" H ", and" a "is₁₁、…、a₆₉When "is an element of the matrix" H ", the following expressions (3) and (4) are satisfied.

[ formula 3 ]

The details of the above formulae (3) and (4) are represented by the following formula (5).

[ formula 4 ]

In addition, the above-described equations (3) to (5) represent the case where the magnetic data input to the arithmetic unit 25 is zero, and the linearization is performed so that the displacement data of 6 degrees of freedom output from the arithmetic unit 25 becomes zero. When the magnetic data input to the arithmetic unit 25 is zero, the vector G is expressed by the following equation (6) using "E" which is a constant term, when the 6-degree-of-freedom displacement data output from the arithmetic unit 25 is a value other than zero.

[ FORMULA 5 ]

G＝HM+E，E＝(e₁，…，e₆)∈R^6×1…(6)

Conversion to x when the displacement data has a value other than zero₁’＝x₁-e₁By setting the variable in the above-described manner, the processing can be performed in the same manner as the conversion when the displacement data becomes zero. In embodiment 1 and embodiment 2 described later, a description will be given without a constant term attached.

The matrix "H" can be based on a vector G that passes through "M" relative to a known vector_n"the measurement data obtained by the measurement" is obtained by a method such as multiple regression analysis. The storage unit 23 stores information of the matrix "H". The arithmetic section 25 performs the secondary magnetic data "M" based on the matrix "H" read from the storage section 23_n"transformation to 6 degrees of freedom displacement data.

The calculation unit 25 may calculate the displacement data based on another expression different from the expressions (3) to (5). The expression used for calculating the displacement data is not limited to an expression containing a first order term of each value, which is magnetic data, and may be an expression containing a higher order term of each value, which is magnetic data.

The sensing apparatus 100 obtains 9 detection results as the detection value of the magnetic flux using 3 sensor units 14a, 14b, 14 c. The 9 detection results are the results of 3 sensor units 14a, 14b, and 14c detecting the values of the magnetic fluxes in the 3-axis directions. The sensing device 100 obtains 6 measurement results as displacement data by an operation based on the 9 detection results. The 6 measurement results are the results of measuring the amount of movement of the 1 st structure 11 in each direction of the 3 axes and the amount of rotation of the 1 st structure 11 about each of the 3 axes. As described above, the number of values as the detection results of the plurality of sensor units 14 is larger than the number of values as the measurement results obtained by the calculation in the calculation unit 25 and the measurement results regarding the movement amount of the 1 st structure 11 and the rotation amount of the 1 st structure 11. That is, the number of dimensions of the detection results obtained by the plurality of sensor units 14 is greater than the number of dimensions of the measurement results obtained by the calculation in the calculation unit 25.

Since the displacement data of 6 degrees of freedom can be calculated by the number of detection values smaller than 9, detection results including redundant data in the movement detection of the operation body are input from the sensor units 14a, 14b, and 14c to the measurement device 20. The sensor apparatus 100 uses the detection result in the determination by the determination section 26, thereby confirming the presence or absence of an abnormality in detection. The number of values as the detection results of each of the plurality of sensor units 14 may be larger than the number of values as the measurement results regarding at least 1 of the movement amount, the rotation amount, and the external force. The sensor device 100 is provided with a plurality of sensor units 14 capable of obtaining a number of values greater than the number of values as measurement results.

Next, the determination by the determination unit 26 will be described. Fig. 4 is a view 1 illustrating a positional relationship between the magnetic sensor and the magnet in the cross section shown in fig. 2. Fig. 4 shows the sensing apparatus 100 in a reference state. In fig. 4 and fig. 5 described later, hatching indicating a cross section is omitted.

In FIG. 4, the vector P₁Is a 3-dimensional vector from the center axis N toward the position of the magnetic sensor 15 a. Vector P₂Is a 3-dimensional vector from the center axis N toward the position of the magnetic sensor 15 b. Vector P₃Is a 3-dimensional vector from the center axis N toward the position of the magnetic sensor 15 c. The position of the magnetic sensor 15 is a position of the magnetic sensor 15 to be a reference for magnetic flux detection.

Vector D₁Is a 3-dimensional vector from the position of the magnetic sensor 15a toward the position of the magnet 16 a. Vector D₁The magnitude and the direction of the magnetic field are determined by the positional relationship between the magnetic sensor 15a and the magnet 16a in the reference state. Vector D₂Is a 3-dimensional vector from the position of the magnetic sensor 15b toward the position of the magnet 16 b. Vector D₂The magnitude and the direction of the magnetic field are determined by the positional relationship between the magnetic sensor 15b and the magnet 16b in the reference state. Vector D₃Is a 3-dimensional vector from the position of the magnetic sensor 15c toward the position of the magnet 16 c. Vector D₃The magnitude and the direction of the magnetic field are determined by the positional relationship between the magnetic sensor 15c and the magnet 16c in the reference state. The position of the magnet 16 is set to the center position in the 3-dimensional direction in the magnet 16.

If the distance between the position of the magnet 16a and the position of the magnet 16c in the 3-dimensional space is set to L₁Then L is₁Represented by the following formula (7). If the distance between the position of the magnet 16a and the position of the magnet 16b in the 3-dimensional space is set to L₂Then L is₂Represented by the following formula (8). If the distance between the position of the magnet 16b and the position of the magnet 16c in the 3-dimensional space is set to L₃Then L is₃Represented by the following formula (9). In addition, in the formulae (7) to(9) And in the formula described later, it is assumed to be "P₁"denotes the vector P₁、“P₂"denotes the vector P₂、“P₃"denotes the vector P₃、“D₁"denotes the vector D₁、“D₂"denotes the vector D₂、“D₃"denotes the vector D₃。

[ formula 6 ]

||P₁+D₁-(P₃+D₃)||＝L₁…(7)

||P₂+D₂-(P₁+D₁)||＝L₂…(8)

||P₃+D₃-(P₂+D₂)||＝L₃…(9)

Fig. 5 is a view 2 illustrating a positional relationship between the magnetic sensor and the magnet in the cross section shown in fig. 2. Fig. 5 shows the sensor device 100 in a state where the 1 st structure 11 has moved from the position in the reference state.

The vector component indicating the relative positional change from the reference state of the magnetic sensor 15a and the magnet 16a is represented by "Δ D₁". The vector component indicating the relative positional change from the reference state of the magnetic sensor 15b and the magnet 16b is represented by "Δ D₂". The vector component indicating the change in position from the reference state is represented by "Δ D" for the magnetic sensor 15c and the magnet 16c₃”。L₁Represented by the following formula (10). L is₂Represented by the following formula (11). L is₃Represented by the following formula (12).

[ formula 7 ]

||P₁+D₁+ΔD₁-(P₃+D₃+ΔD₃)||＝L₁…(10)

||P₂+D₂+ΔD₂-(P₁+D₁+ΔD₁)||＝L₂…(11)

||P₃+D₃+ΔD₃-(P₂+D₂+ΔD₂)||＝L₃…(12)

Magnet 16a, magnet 16b, and magnet16c are all provided in the 2 nd structure 12 of the rigid body, L₁、L₂And L₃In the reference state and after the 1 st structure 11 is moved from the reference state.

With respect to "D₁+ΔD₁"length and" D₃+ΔD₃"the correlation between the length of" and "Δ D" represented by the formula (10)₁"length and" Δ D₃The length of "remains unchanged regardless. With respect to "D₁+ΔD₁"length and" D₂+ΔD₂"the correlation between the length of" and "Δ D" represented by the formula (11)₁"length and" Δ D₂The length of "remains unchanged regardless. With respect to "D₂+ΔD₂"length and" D₃+ΔD₃"the correlation between the length of" and "Δ D" represented by the formula (12)₂"length and" Δ D₃The length of "remains unchanged regardless.

However, any of the magnetic sensors 15a, 15b, 15c is influenced by the magnetic field existing outside the sensor device 100 to have the magnetic data "M_n"if there is a change, the correlation represented by the expressions (10) to (12) does not hold. Not only when influenced by the magnetic field, but also when the magnetic data "M" is caused to occur, such as when an abnormality occurs in any of the magnetic sensors 15a, 15b, and 15c during operation_n"in the case of a changed situation, the correlation does not hold. When the correlation is disturbed, the determination unit 26 determines that a detection abnormality has occurred. The detection abnormality is an abnormality in which the detection result changes due to a factor other than a change in the relative position of the magnetic sensor 15 and the magnet 16. When a detection abnormality occurs, the sensor device 100 cannot normally detect the operation of the 1 st structure 11.

The determination unit 26 determines that no detection abnormality has occurred when all of the following expressions (13) to (15) are satisfied. The determination unit 26 determines that a detection abnormality has occurred when at least 1 of the following expressions (13) to (15) is not satisfied.

[ formula 8 ]

|L₁-||P₁+D₁+ΔD₁-(P₃+D₃+ΔD₃)|||≤ΔL₁…(13)

|L₂-||P₂+D₂+ΔD₂-(P₁+D₁+ΔD₁)|||≤ΔL₂…(14)

|L₃-||P₃+D₃+ΔD₃-(P₂+D₂+ΔD₂)|||≤ΔL₃…(15)

P in the above formula (13)₁+D₁+ΔD₁-(P₃+D₃+ΔD₃) The | | | represents the result obtained by obtaining the distance between the magnet 16a and the magnet 16 c. Δ L₁Is used for judging L₁And P₁+D₁+ΔD₁-(P₃+D₃+ΔD₃) Whether the difference of | is a threshold value of an error of noise or the like. P in the above formula (14)₂+D₂+ΔD₂-(P₁+D₁+ΔD₁) The | | | represents the result obtained by obtaining the distance between the magnet 16a and the magnet 16 b. Δ L₂Is used for judging L₂And P₂+D₂+ΔD₂-(P₁+D₁+ΔD₁) Whether the difference of | is a threshold value of an error of noise or the like. P in the above formula (15)₃+D₃+ΔD₃-(P₂+D₂+ΔD₂) The | | | represents the result obtained by obtaining the distance between the magnet 16b and the magnet 16 c. Δ L₃Is used for judging L₃And P₃+D₃+ΔD₃-(P₂+D₂+ΔD₂) Whether the difference of | is a threshold value of an error of noise or the like.

When a detection abnormality occurs, the above-described correlation becomes not established, and L is thereby caused₁And P₁+D₁+ΔD₁-(P₃+D₃+ΔD₃) Difference of | |, L₂And P₂+D₂+ΔD₂-(P₁+D₁+ΔD₁) The difference of | | and L₃And P₃+D₃+ΔD₃-(P₂+D₂+ΔD₂) At least any of the differences of | |One is greater than the error. Thus, the determination unit 26 can determine whether or not a detection abnormality has occurred based on expressions (13) to (15).

As described above, the determination unit 26 determines the presence or absence of a detection abnormality based on the result of determining the distances between the magnets 16a, 16b, and 16c, which are the elements arranged in the 2 nd structure 12. The determination unit 26 may determine the presence or absence of a detection abnormality based on a result of determining the distance between the magnetic sensors 15a, 15b, and 15c, which are the elements arranged in the 1 st structure 11.

Fig. 6 is a flowchart for explaining the operation of the sensor device according to embodiment 1. The magnetic sensors 15a, 15b, and 15c detect magnetic fluxes when the 1 st structure 11 is operated. In step S1, the acquisition unit 21 acquires magnetic data detected by the magnetic sensors 15a, 15b, and 15 c. The arithmetic unit 25 calculates the amount of movement of the 1 st structure 11 and the amount of rotation of the 1 st structure 11 based on the magnetic data obtained in step S1. The measuring device 20 obtains the measurement results of the movement amount and the rotation amount of the 1 st structure 11 by the calculation performed by the calculating unit 25.

In step S2, the determination unit 26 determines whether or not the conditional expressions, that is, the expressions (13) to (15), are satisfied based on the magnetic data obtained in step S1. When determining that the conditional expression is satisfied (Yes at step S2), the determination unit 26 determines that the detection abnormality has not occurred. The output unit 24 outputs the measurement result obtained by the calculation in the calculation unit 25.

On the other hand, when determining that the conditional expression is not satisfied (No at step S2), the determination unit 26 determines that a detection abnormality has occurred. The output unit 24 does not output the measurement result, but outputs an alarm in step S3. As described above, the sensor device 100 ends the operation according to the sequence shown in fig. 6.

Next, a hardware configuration of the measurement device 20 will be described. The functions of the measurement device 20 are realized using a processing circuit. The processing circuit is dedicated hardware mounted on the measurement device 20. The processing circuitry may be a processor executing a program stored in memory.

Fig. 7 is a diagram 1 showing an example of the hardware configuration of the measurement apparatus according to embodiment 1. Fig. 7 shows a hardware configuration in the case where the function of the measurement device 20 is realized by using dedicated hardware. The measurement device 20 includes a processing circuit 41 for executing various processes, an external storage device 42 for storing various information, and an input/output interface 43 as a connection interface with an external device of the measurement device 20. The input-output interface 43 may have an input device for information input such as a keyboard or a pointing device, or an output device for information output such as a display device or a sound device. The respective parts of the measurement device 20 shown in fig. 7 are connected to each other via a bus.

The dedicated hardware, i.e., the processing circuit 41, is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an asic (application Specific Integrated circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof. Each function of the arithmetic unit 25 and the determination unit 26 shown in fig. 3 is realized by using the processing circuit 41. The external storage device 42 is an HDD (hard Disk drive) or an SSD (solid State drive). The function of the storage unit 23 is realized using the external storage device 42. The functions of the acquisition unit 21 and the output unit 24 are realized using the input/output interface 43.

Fig. 8 is a diagram 2 showing an example of the hardware configuration of the measurement device according to embodiment 1. Fig. 8 shows a hardware configuration in the case where the function of the measurement device 20 is realized by using hardware for executing a program. The processor 44 and the memory 45 are connected to the external storage device 42 and the input/output interface 43.

The processor 44 is a cpu (central Processing unit), a Processing device, an arithmetic device, a microprocessor, a microcomputer, or a dsp (digital Signal processor). The functions of the arithmetic unit 25 and the determination unit 26 shown in fig. 3 are realized by the processor 44 and software, firmware, or a combination of software and firmware. The software or firmware is described as a program and stored in the memory 45 as an internal memory. The Memory 45 is a nonvolatile or volatile semiconductor Memory, and is a ram (random Access Memory), a rom (Read Only Memory), a flash Memory, an eprom (Erasable Programmable Read Only Memory), or an EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory).

According to embodiment 1, the determination unit 26 determines the presence or absence of a change in magnetic flux caused by factors other than a change in the relative position of the magnetic sensor 15 and the magnet 16, based on the detection results of the sensor units 14a, 14b, and 14 c. The determination unit 26 determines the presence or absence of an abnormality based on the result of determining the distance between the elements disposed in the 1 st structure 11 among the magnetic sensors 15a, 15b, and 15c and the magnets 16a, 16b, and 16c, or the result of determining the distance between the elements disposed in the 2 nd structure 12. Thus, the sensor device 100 has an effect of being able to confirm the occurrence of an abnormality at the time of detection.

In embodiment 1, the measurement device 20 is provided integrally with the 1 st structure 11 and the 2 nd structure 12 constituting the sensor device 100. The function of the sensor device 100 can be realized by using a device provided at a position distant from the 1 st structure 11 and the 2 nd structure 12.

Fig. 9 is a diagram illustrating a modification of embodiment 1. The sensor system 200 according to the modification includes the sensor 101 and the measurement device 28. The sensor device 101 has the 1 st structure 11 and the 2 nd structure 12. The sensing device 101 and the assay arrangement 28 can be communicatively connected to each other. The sensor device 101 and the measurement device 28 are connected via a network for wireless communication or a network for wired communication. The sensor apparatus system 200 achieves the same function as the sensor apparatus 100 shown in fig. 3 by the sensor apparatus 101 and the measurement device 28 being capable of communicating with each other.

The sensor device 101 is provided with a communication unit 17 in place of the measurement device 20 shown in fig. 3. The measurement device 28 is provided with a communication unit 27 in place of the acquisition unit 21. The communication unit 17 is realized by using a communication interface that performs communication with an external device of the sensor apparatus 101. The communication unit 27 is realized using a communication network that performs communication with an external device of the measurement device 28. The sensor system 200 according to the present modification can check that an abnormality has occurred at the time of detection, as in the sensor system 100 described above.

In embodiment 1, the sensing device 100 will be sensed magnetically9 values x obtained by the devices 15a, 15b, 15c₁、y₁、z₁、x₂、y₂、z₂、x₃、y₃、z₃A transformation is performed to the displacement data. In addition, the sensing device 100 is based on the signal L₁、L₂、L₃Whether or not the detection abnormality occurs is determined by determining whether or not the correlation determined without change is established. The calculation unit 25 can obtain displacement data of 6 degrees of freedom by using at least 6 of the 9 values. In embodiment 2 to be described next, the sensor device 100 calculates displacement data by changing the selection pattern of the value used for calculation of the displacement data among the 9 values, and determines whether or not a detection abnormality has occurred based on whether or not the calculated displacement data matches.

Embodiment 2.

Fig. 10 is a flowchart for explaining the operation of the sensor device according to embodiment 2 of the present invention. In embodiment 2, the arithmetic unit 25 obtains displacement data based on a value selected from the magnetic data obtained by the magnetic sensors 15a, 15b, and 15 c. The calculation unit 25 calculates displacement data by changing the selection pattern of the values from the magnetic data. The determination unit 26 determines whether or not a detection abnormality has occurred based on whether or not the displacement data calculated by changing the selection pattern matches. In embodiment 2, the same components as those in embodiment 1 are denoted by the same reference numerals, and the description will be mainly given of a configuration different from that in embodiment 1.

In step S11, the acquisition unit 21 acquires 9 values "x" as magnetic data₁、y₁、z₁、x₂、y₂、z₂、x₃、y₃、z₃". In step S12, the arithmetic unit 25 calculates displacement data for each of the plurality of data sets. The arithmetic unit 25 includes "x" detected by the magnetic sensor 15a₁，y₁，z₁"x obtained by detection in the magnetic sensor 15b, at least 1 of" x₂，y₂，z₂At least 1 of "and" x "obtained by detection in the magnetic sensor 15c₃，y₃，z₃"at least 1 of them.

Here, the calculation unit 25 obtains displacement data of 6 degrees of freedom using 6 of the 9 values. The arithmetic unit 25 uses "x" which is the 1 st data set composed of 6 values selected from 9 values₁、y₁、x₂、y₂、x₃、y₃"to obtain displacement data. The matrix for converting the 1 st data set to the displacement data of 6 degrees of freedom is set as "I", and "b" is set as₁₁、…、b₆₆When "is an element of the matrix" I ", the following expression (16) holds.

[ formula 9 ]

The arithmetic unit 25 calculates the pattern based on "x" which is a 2 nd data set in which the selected pattern is different from the 1 st data set₁、y₁、z₁、x₂、y₂、x₃"to obtain displacement data. The matrix for converting the 2 nd data set to the displacement data of 6 degrees of freedom is set as "I", and "b'₁₁、…、b’₆₆When "is an element of the matrix" I ", the following expression (17) holds.

[ formula 10 ]

In the case where any of the magnetic sensors 15a, 15b, 15c changes in magnetic data due to the influence of a magnetic field existing outside the sensing apparatus 100, a difference occurs in the calculation result of the displacement data. The determination unit 26 compares the displacement data calculated using the 1 st data set with the displacement data calculated using the 2 nd data set. In step S13, the determination unit 26 determines whether or not the displacement data calculated for each of the plurality of data sets match.

The determination unit 26 determines that no detection abnormality has occurred when the displacement data calculated using the 1 st data set and the displacement data calculated using the 2 nd data set match. The determination unit 26 determines that no detection abnormality has occurred when the displacement data obtained using the 1 st data set and the displacement data obtained using the 2 nd data set do not match. The determination unit 26 may determine the presence or absence of a detection abnormality based on whether or not the displacement data about 3 or more data sets match each other.

When the displacement data calculated for each of the plurality of data sets match (Yes at step S13), the determination unit 26 determines that no detection abnormality has occurred. The output unit 24 outputs the measurement result obtained by the calculation in the calculation unit 25.

On the other hand, when the displacement data calculated for each of the plurality of data sets do not match (No at step S13), the determination unit 26 determines that a detection abnormality has occurred. The output unit 24 does not output the measurement result, but outputs an alarm in step S14. As described above, the sensor apparatus 100 ends the operation according to the sequence shown in fig. 10.

The calculation unit 25 may obtain the displacement data based on a data set including 7 values selected from 9 values. The arithmetic section 25 calculates "x" based on 7 values₁、y₁、z₁、x₂、y₂、x₃、y₃"to obtain displacement data. A matrix for converting the data set into displacement data with 6 degrees of freedom is represented by "J", and "c" is represented by₁₁、…、c₆₇When "is an element of the matrix" J ", the following expression (18) holds.

[ formula 11 ]

The calculation unit 25 may calculate the displacement data based on a data set including 8 values selected from 9 values. Even when 7 or 8 values are selected from the magnetic data, the arithmetic unit 25 can calculate the displacement data by changing the selection pattern of the values from the magnetic data. The determination unit 26 can determine the presence or absence of a detection abnormality based on whether or not the displacement data for the plurality of data sets match each other.

According to embodiment 2, the calculation unit 25 obtains a plurality of pieces of displacement data by changing the selection pattern of values used for calculation of the displacement data. The determination unit 26 determines whether or not there is an abnormality based on whether or not the plurality of calculated displacement data match. Thus, the sensor device 100 has an effect of being able to confirm the occurrence of an abnormality at the time of detection. Note that the same functions as those of the sensor device 100 according to embodiment 2 can be realized by the sensor device system 200 described above.

In embodiments 1 and 2, the number of sensor units 14 provided in the sensor devices 100 and 101 is not limited to 3, and may be less than 3 or more than 3. The number of sensor units 14 may be arbitrarily changed in accordance with the degree of freedom desired with respect to the displacement data. The sensor devices 100 and 101 may be provided with 2 sensor units 14 capable of detecting a change in the relative positions of the magnetic sensor 15 and the magnet 16 in each direction of the 3 axes, thereby detecting the translational motion of the 1 st structure 11 in each direction of the 3 axes. In addition, in the sensor devices 100, 101, in addition to the sensor unit 14 that detects the relative positional change of the magnetic sensor 15 and the magnet 16 in each direction of the 3-axis, the sensor unit 14 that detects the relative positional change of the magnetic sensor 15 and the magnet 16 in each direction of the 2-axis or the direction of the 1-axis may be provided. In embodiment 2, the calculation unit 25 may select values detected by 4 or more magnetic sensors 15 to obtain displacement data.

The 1 st structure 11 and the 2 nd structure 12 are not limited to being connected by the elastic body 13. The 1 st structure 11 and the 2 nd structure 12 may be the 1 st structure 11 that can perform a translational motion or a rotational motion with respect to the 2 nd structure 12. The sensor devices 100 and 101 may have a linear guide for translationally moving the 1 st structure 11 instead of the elastic body 13.

The sensing devices 100, 101 can be used in input devices of robots. The sensor devices 100 and 101, which are input devices of the robot, measure the movement of the operating body when the human touches the operating body or the force applied to the operating body when the human touches the operating body, and output the measurement results to the control device of the robot. The control device causes the robot to perform a translational motion and a rotational motion according to the measurement result. As described above, the sensor devices 100 and 101 can be used as input devices for operating the robot in accordance with human operations.

The sensor device 100 and the sensor device system 200 may determine the presence or absence of an abnormality by a method other than the above-described calculation. The sensor device 100 and the sensor device system 200 can obtain measurement results regarding at least 1 of the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, and the external force applied to the 1 st structure 11 by a method other than the above-described calculation. In embodiment 3, a case will be described in which the presence or absence of an abnormality is determined by 1 machine learning which is a method other than the above-described calculation. In embodiment 4, a case will be described in which measurement results regarding at least 1 of the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, and the external force applied to the 1 st structure 11 are obtained by machine learning of 1 as a method other than the above-described calculation.

Embodiment 3.

Fig. 11 is a diagram showing a functional configuration of a sensor device according to embodiment 3 of the present invention. In embodiment 3, the same components as those in embodiments 1 and 2 are denoted by the same reference numerals, and configurations different from those in embodiments 1 and 2 will be mainly described.

The sensor device 102 according to embodiment 3 includes the measurement device 50. The measurement device 50 includes an acquisition unit 21, a control unit 51 for controlling the measurement device 50, a teacher data acquisition unit 53 for acquiring teacher data, a storage unit 23, and an output unit 24. The control unit 51 includes a determination unit 52, and the determination unit 52 determines whether or not there is an abnormality based on the detection results of the sensor units 14a, 14b, and 14 c. Determination unit 52 includes learning unit 54.

The teacher data is at least 1 of the external magnetic information 55, which is information related to the presence of external magnetism, the result of obtaining the distances between the magnetic sensors 15a, 15b, and 15c, which are the plurality of elements arranged in the 1 st structure 11, and the result of obtaining the distances between the magnets 16a, 16b, and 16c, which are the plurality of elements arranged in the 2 nd structure 12. The external magnetism is magnetism generated outside the sensing device 102.

The learning unit 54 learns the presence or absence of a detection abnormality of the sensor device 102 in accordance with the data set. The data set is a combination of state variables and teacher data. The state variable includes the detection result of each of the sensor units 14a, 14b, and 14 c. The acquisition unit 21 functions as a state observation unit that observes a state variable. The acquisition unit 21, the teacher data acquisition unit 53, and the learning unit 54 function as a machine learning device that executes machine learning. The function of the determination unit 52 having the learning unit 54 is realized by using the same processing circuit as that of embodiment 1. The function of the teacher data acquisition unit 53 is realized by using the input/output interface 43 similar to that in embodiment 1.

The teacher data acquisition unit 53 acquires the detection results of the magnetic fluxes obtained by the magnetic sensors 15a, 15b, and 15c, that is, the respective values, from the acquisition unit 21. The teacher data acquisition unit 53 calculates each value of the magnetic flux as L, which is the distance between the position of the magnet 16a and the position of the magnet 16c₁L, which is the distance between the position of the magnet 16a and the position of the magnet 16b₂And L which is the distance between the position of the magnet 16b and the position of the magnet 16c₃And (6) carrying out transformation. The teacher data acquisition unit 53 checks for the presence or absence of L₁、L₂And L₃The change of (b) is determined, and teacher data as a result of the determination is acquired. The teacher data acquisition unit 53 outputs the acquired teacher data to the learning unit 54.

The learning unit 54 acquires values from the acquisition unit 21, which are detection results of the magnetic fluxes obtained by the magnetic sensors 15a, 15b, and 15 c. The learning unit 54 determines the sum of the values of the magnetic fluxes as the state variables and the presence/absence of L₁、L₂And L₃The teacher data of the change-related determination result are associated with each other, thereby creating a data set. The learning unit 54 learns whether or not the detection result obtained by the calculation unit 25 is normal based on the data set. An abnormality in the detection result may occur in the case where the sensor unit 14 is affected by external magnetism or in the case where the sensor unit 14 malfunctions.

The teacher data acquisition unit 53 may determine whether or not there is a variation in the distance between the magnetic sensors 15a, 15b, and 15c, and acquire teacher data as a result of the determination. The teacher data acquisition unit 53 can acquire teacher data as the external magnetic information 55. The external magnetic information 55 is information indicating the presence or absence of external magnetism that can affect the output of the sensor unit 14. In this case, external magnetic information 55 as a result of the magnetic measurement is input from the external measurement device to the teacher data acquisition unit 53. The external measurement instrument is a measurement instrument provided outside the sensor device 102. In addition, in the case where a device that generates magnetism in accordance with the driving state is provided outside the sensor device 102, the external magnetic information 55 may be information indicating the driving state of the device. In this case, the external magnetic information 55 is input from the device to the teacher data acquisition unit 53. In fig. 11, an external measurement device is not shown.

The learning unit 54 may learn whether or not the detection result obtained by the arithmetic unit 25 is normal, and may also learn the indication L₁、L₂、L₃Or a value similar to the information indicating the degree of variation. In this case, means for determining whether or not the detection result obtained by the arithmetic unit 25 is normal is provided at a stage subsequent to the learning unit 54 in the determination unit 52. This section refers to the output value from the learning section 54 to determine whether or not the detection result obtained by the calculation section 25 is normal.

The state variable input to the learning unit 54 is not limited to the detection values obtained by the magnetic sensors 15a, 15b, and 15c, and may be information obtained by arithmetic processing on the detection values. The calculation unit 25 calculates the displacement amount of the 1 st structure 11 by calculation processing on the detection value, and can output the state variable, which is the calculated value, to the learning unit 54.

In embodiment 3, as in embodiment 1, the number of detection values input to the acquisition unit 21 is larger than the number of measurement result values obtained by the calculation in the calculation unit 25. The sensor device 102 is provided with a plurality of sensor units 14 capable of obtaining a larger number of detection values than the number of measurement result values.

According to embodiment 3, the sensor device 102 learns the presence or absence of an abnormality in accordance with the data set, thereby making it possible to determine the presence or absence of an abnormality with high accuracy. According to embodiment 3, as compared with the case where the processing calculation for determining the presence or absence of an abnormality is derived by the manual operation of the designer, the work required for the design and installation of the determination unit 52 can be reduced. Therefore, the sensing device 102 can reduce the design work cost.

The learning in embodiment 3 may be performed at the time of manufacturing the sensor device 102, or may be performed at the time of adjustment in the use environment of the sensor device 102. The sensor device 102 can correct individual differences due to the characteristics of the magnetic sensor 15 and the magnet 16 or can correct individual differences due to the installation positions of the magnetic sensor 15 and the magnet 16 by learning at the time of manufacturing the sensor device 102. The sensor device 102 can perform highly accurate determination of the presence or absence of an abnormality by correcting individual differences at the time of manufacture.

In addition, regarding a robot or the like mounted with the sensor device 102, the sensor device 102 can perform learning in a use environment when the robot or the like is started up and adjustment for use start is performed. The sensor device 102 can reduce the adjustment work cost at the start of startup and use by learning in the use environment. In addition, the sensing device 102 can determine the presence or absence of an abnormality with high accuracy in accordance with the usage environment by learning in the usage environment.

The learning unit 54 stores the learning result. The determination unit 52 determines whether there is an abnormality based on the information input to the determination unit 52 and the learning result, and outputs the determination result. Upon application of the sensing device 102, the sensing device 102 can stop the learning by the learning section 54. The sensing device 102 stops learning, whereby input of teacher data to the learning section 54 is not required. The sensor device 102 does not need to input teacher data, and thus does not need to acquire the external magnetic information 55, the process of determining the distances between the magnetic sensors 15a, 15b, 15c, and the process of determining the distances between the magnets 16a, 16b, 16 c.

When the sensor device 102 is used, it is not necessary to acquire the external magnetic information 55, and thus an external measurement instrument for measuring the external magnetism is not necessary. Thus, the sensor device 102 can accurately determine whether or not there is an abnormality in the application while suppressing the application cost to a low level. When the sensor device 102 is applied, the process of determining the distances between the magnetic sensors 15a, 15b, and 15c and the process of determining the distances between the magnets 16a, 16b, and 16c can be stopped, and therefore the sensor device 102 can reduce the resources for the process performed by the determination unit 52. The sensor device 102 can increase the speed of the process performed by the determination unit 52 by stopping the process of determining the distance between the magnetic sensors 15a, 15b, and 15c and the process of determining the distance between the magnets 16a, 16b, and 16 c.

The sensing device 102 can appropriately acquire teacher data at the time of application, and can perform learning in the middle of application by the learning unit 54. The sensing device 102 can accurately determine the presence or absence of an abnormality in accordance with a change in the environment by learning based on teacher data at the time of application. L, which is a distance indicating a criterion for determining whether there is an abnormality, is set in the learning unit 54₁、L₂And L₃When learning the value of the degree of fluctuation of the sensor device 102, the sensor device can be protected from maintenance to warn of the sign of an abnormality by referring to the value output from the learning unit 54, that is, the value indicating the degree of fluctuation. Note that the sensor system 200 according to embodiment 1 or the sensor device 100 according to embodiment 2 can perform the same learning as the sensor device 102 according to embodiment 3.

Embodiment 4.

Fig. 12 is a diagram showing a functional configuration of a sensor device according to embodiment 4 of the present invention. In embodiment 4, the same components as those in embodiments 1 to 3 are denoted by the same reference numerals, and configurations different from those in embodiments 1 to 3 will be mainly described.

The sensor device 103 according to embodiment 4 includes the measurement device 60. The measurement device 60 includes an acquisition unit 21, a control unit 61 for controlling the measurement device 60, a teacher data acquisition unit 63 for acquiring teacher data, a storage unit 23, and an output unit 24. The controller 61 includes a calculation unit 62, and the calculation unit 62 calculates a measurement result regarding at least 1 of the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, and the external force applied to the 1 st structure 11 by calculation based on the detection results of the sensor units 14a, 14b, and 14 c. The arithmetic unit 62 includes a learning unit 64.

The teacher data is the result of actually measuring the movement amount of the 1 st structure 11 and the result of actually measuring the rotation amount of the 1 st structure 11. The learning unit 64 learns the presence or absence of a detection abnormality related to the sensing device 103, in accordance with the data set. The data set is a combination of state variables and teacher data. The state variable includes the detection result of each of the sensor units 14a, 14b, and 14 c. The acquisition unit 21 functions as a state observation unit that observes a state variable. The acquisition unit 21, the teacher data acquisition unit 63, and the learning unit 64 function as a machine learning device that executes machine learning. The function of the arithmetic unit 62 including the learning unit 64 is realized by using the same processing circuit as that of embodiment 1. The function of the teacher data acquisition unit 63 is realized by using the input/output interface 43 similar to that in embodiment 1.

The external measurement instrument 65 is a measurement instrument provided outside the sensor device 103. The external measuring device 65 measures the amount of movement of the 1 st structure 11 and the amount of rotation of the 1 st structure 11. The teacher data acquisition unit 63 acquires teacher data, which is a result of actual measurement of the movement amount and the rotation amount, from the external measurement device 65. The teacher data acquisition unit 63 outputs the acquired teacher data to the learning unit 64.

The learning unit 64 acquires values of the detection results of the magnetic fluxes acquired by the magnetic sensors 15a, 15b, and 15c from the acquisition unit 21. The learning unit 64 creates a data set by associating the value of the magnetic flux as the state variable and teacher data as the measurement result of the movement amount and the rotation amount with each other. The learning unit 64 learns the measurement results of the movement amount of the 1 st structure 11 and the rotation amount of the 1 st structure 11 based on the data set.

The teacher data may be the result of actual measurement of the external force applied to the 1 st structure 11. In this case, the teacher data acquiring unit 63 acquires the actual measurement result of the external force applied to the 1 st structure 11 from the external measuring device 65. In addition, the learning section 64 creates a data set by associating the value of the magnetic flux as the state variable and teacher data as the actual measurement result of the external force with each other. The learning unit 64 learns the external force applied to the 1 st structure 11 based on the data set.

The external force learned by the learning unit 64 is composed of 6 components in total, namely, a translational force component, which is a force component for translationally moving the 1 st structure 11 in each direction of the 3 axes, and a torque component, which is a force component for rotationally moving the 1 st structure 11 about each of the 3 axes. The external force learned by the learning unit 64 may be any combination of any of the 6 components as long as it is at least 1 of the 6 components.

As described above, the teacher data acquiring unit 63 may acquire at least 1 of the result of actually measuring the movement amount of the 1 st structure 11, the result of actually measuring the rotation amount of the 1 st structure 11, and the result of actually measuring the external force applied to the 1 st structure 11. The learning unit 64 may learn measurement results regarding at least 1 of the movement amount, the rotation amount, and the external force.

The state variables input to the learning unit 64 are not limited to the detection values of the magnetic sensors 15a, 15b, and 15c, and may be information obtained by arithmetic processing on the detection values. The calculation unit 62 calculates the displacement amount of the 1 st structure 11 by calculation processing on the detection value, and can input the state variable, which is the calculated value, to the learning unit 54.

In embodiment 4, as in embodiment 1, the number of detection values input to the acquisition unit 21 is larger than the number of measurement result values obtained by the calculation in the calculation unit 62. The sensor device 103 is provided with a plurality of sensor units 14 capable of obtaining a larger number of detection values than the number of measurement result values.

According to embodiment 4, the sensor device 103 learns the measurement results regarding the movement amount, the rotation amount, or the external force from the data set, and thereby can obtain a highly accurate measurement result regarding the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, or the external force applied to the 1 st structure 11. According to embodiment 4, as compared with the case where the processing calculation for obtaining the measurement result is derived by the manual work of the designer, the work required for designing the calculation unit 62 and mounting the calculation unit 62 can be reduced. Therefore, the sensing apparatus 103 can reduce the design work cost.

The learning in embodiment 4 may be performed at the time of manufacturing the sensor device 103, or may be performed at the time of adjustment in the use environment of the sensor device 103. The sensor device 103 can correct individual differences due to the characteristics of the magnetic sensor 15 and the magnet 16 or the individual differences due to the installation positions of the magnetic sensor 15 and the magnet 16 by learning at the time of manufacturing the sensor device 103. The sensor device 103 can obtain a highly accurate measurement result by correcting the individual difference at the time of manufacturing.

In addition, with respect to a robot or the like mounted with the sensor device 103, the sensor device 103 can perform learning in a use environment when the robot or the like is started up and adjustment for use start is performed. The sensing device 103 can reduce the adjustment work cost at the start and the start of use by learning in the use environment. In addition, the sensing device 103 can obtain a measurement result with high accuracy in accordance with the usage environment by learning in the usage environment.

The learning unit 64 stores the learning result. The arithmetic unit 62 calculates the measurement result based on the information input to the arithmetic unit 62 and the learning result, and outputs the measurement result. Upon application of the sensing device 103, the sensing device 103 can stop learning by the learning section 64. The sensing device 103 does not need teacher data input to the learning section 64 by stopping learning. The sensing device 102 does not need to input teacher data and thus does not need to take actual measurements from the external measurement instrument 65.

In the application of the sensing device 103, no actual measurements need to be taken, and thus no external measuring instrument 65 is required. Thus, the sensor device 103 can obtain a measurement result with high accuracy in application while suppressing the application cost to a low level. The sensing device 103 can acquire teacher data as appropriate at the time of application, and can perform learning in the middle of application by the learning unit 64. The sensing device 103 can obtain a highly accurate measurement result in accordance with the change in the environment by learning based on teacher data at the time of application. Note that the sensor system 200 according to embodiment 1 or the sensor device 100 according to embodiment 2 can perform the same learning as the sensor device 103 according to embodiment 4.

The sensing apparatus can perform both the learning in embodiment 3 and the learning in embodiment 4 described above. Fig. 13 is a diagram showing an example of a sensing device that performs both learning in embodiment 3 and learning in embodiment 4. The sensor device 104 shown in fig. 13 learns the presence or absence of an abnormality, as in the sensor device 102 according to embodiment 3. In addition, the sensor device 104 learns the measurement results regarding at least 1 of the movement amount, the rotation amount, and the external force, as in the sensor device 103 according to embodiment 4.

The sensing device 104 has an assay means 70. The measurement device 70 includes an acquisition unit 21, a control unit 71 for controlling the measurement device 70, a teacher data acquisition unit 73 for acquiring teacher data, a storage unit 23, and an output unit 24. The control unit 71 includes a learning unit 74. The teacher data acquisition unit 73 has the function of the teacher data acquisition unit 53 shown in fig. 11 and the function of the teacher data acquisition unit 63 shown in fig. 12. The learning unit 74 has the function of the learning unit 54 shown in fig. 11 and the function of the learning unit 64 shown in fig. 12. The control unit 71 has the functions of the control unit 51 shown in fig. 11 and the control unit 61 shown in fig. 12. In fig. 13, the components of the control unit 71 other than the learning unit 74 are not shown.

The sensing device 104 can perform high-precision determination of the presence or absence of an abnormality by learning the presence or absence of an abnormality in accordance with the data set. Further, the sensing device 104 learns the measurement results regarding the movement amount, the rotation amount, or the external force from the data set, and thereby can obtain a highly accurate measurement result regarding the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, or the external force applied to the 1 st structure 11.

In the learning unit 74 in which the learning function of embodiment 3 and the learning function of embodiment 4 are integrated, a part of the processing of the input layers and the like relating to the learning functions of both can be generalized. Therefore, the sensing device 104 can reduce the processing load for learning. The learning unit 74 can reflect the determination result of the presence or absence of an abnormality in the calculation of the measurement result. The learning unit 74 can reduce the weight in the calculation of the measurement result with respect to the value that becomes the cause of the abnormality among the detection results obtained by the magnetic sensor 15. The sensing device 104 reflects the determination result of the presence or absence of an abnormality in the calculation of the measurement result, and thereby can obtain a highly accurate measurement result even when an environmental change such as an abnormality occurs in the measurement result. Note that the sensor system 200 according to embodiment 1 or the sensor device 100 according to embodiment 2 can perform the same learning as the sensor device 104.

The learning in embodiments 3 and 4 is not limited to the learning units 54, 64, and 74 that use the internal components of the sensor devices 102, 103, and 104. The learning unit may be provided in an external device connected to the sensor devices 102, 103, and 104 via a network. A learning unit provided in the external device acquires teacher data and state variables from the sensing devices 102, 103, and 104 via a network. The learning result obtained by the learning unit provided in the external device is transmitted to the sensor devices 102, 103, and 104 via the network. The learning portion may reside on a cloud server.

The learning units 54 and 74 learn the presence or absence of an abnormality by so-called teacher learning, for example, according to a neural network model. The learning units 64 and 74 learn measurement results relating to the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, or the external force applied to the 1 st structure 11, for example, by what is called teacher learning, in accordance with a neural network model. Here, the teacher learning refers to a model in which a large number of data sets including an input and a label that is a result corresponding to the input are given to the learning units 54, 64, and 74, and the learning units 54, 64, and 74 learn the features of the data sets and estimate the result from the input.

The neural network is composed of an input layer composed of a plurality of neurons, a hidden layer which is an intermediate layer composed of a plurality of neurons, and an output layer composed of a plurality of neurons. The intermediate layer may be 1 layer or 2 or more layers.

Fig. 14 is a diagram showing an example of the configuration of the neural network used for learning in embodiments 3 and 4. The neural network shown in fig. 14 is a layer 3 neural network. The input layer contains neurons X1, X2, X3. The middle layer contains neurons Y1, Y2. The output layer contains the neurons Z1, Z2, Z3. In addition, the number of neurons of each layer is arbitrary. The values input to the input layer are multiplied by weights W1, i.e., W11, W12, W13, W14, W15, and W16, and input to the middle layer. The plurality of values input to the intermediate layer are multiplied by weights W2, i.e., W21, W22, W23, W24, W25, and W26, and output from the output layer. The output result outputted from the output layer changes in accordance with the values of the weights W1, W2.

The neural networks of the learning units 54, 74 learn the presence or absence of an abnormality in the detection by the sensing devices 102, 104. The neural network learns the relationship between the state variables and the presence or absence of an abnormality by so-called teacher learning, in accordance with a data set created based on a combination of the state variables observed by the acquisition unit 21 and the teacher data acquired by the teacher data acquisition units 53 and 73. In this case, the neural network learns the relationship by adjusting the weights W1, W2 so that the result of the output from the output layer upon input of the detection result obtained by the sensor unit 14 to the input layer approaches the information on the presence of the external magnetism, the result obtained by obtaining the distances between the magnetic sensors 15a, 15b, 15c, or the teacher data which is the result obtained by obtaining the distances between the magnets 16a, 16b, 16 c.

The neural networks of the learning units 64 and 74 learn measurement results relating to the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, or the external force applied to the 1 st structure 11. The neural network learns the relationship between the state variables and the measurement results by so-called teacher-present learning, in accordance with a data set created based on a combination of the state variables observed by the acquisition unit 21 and the teacher data acquired by the teacher data acquisition units 53 and 73. In this case, the neural network learns the relationship by adjusting the weights W1, W2 so that the result of the detection result obtained by the sensor unit 14 being input to the input layer and output from the output layer approaches the teacher data, which is the actual measurement result regarding the movement amount, the rotation amount, or the external force.

The neural network can also learn the presence or absence of an abnormality in detection by the sensing devices 102 and 104 by so-called teachers-less learning. The neural network can also learn measurement results related to the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, or the external force applied to the 1 st structure 11 by so-called teachers-less learning. The teachers-less learning is a model in which the learning units 54, 64, and 74 learn what distribution of input data is by giving a large amount of input data to the learning units 54, 64, and 74 without giving corresponding teacher output data.

There are 1 clustering that packetizes input data based on similarity of the input data in the teacher-less learning method. The learning units 54, 64, and 74 generate output prediction models by performing output allocation so as to optimize a certain criterion using the result of clustering. The learning units 54, 64, and 74 can learn whether there is an abnormality or a measurement result by learning with a half teacher, which is a model combining the learning with the teacher. The teacher output data is given to a part of the input data, and the half-teacher learning is performed when the teacher output data is not given to the other input data.

The learning units 54 and 74 may learn the presence or absence of an abnormality in detection of the sensor devices 102 and 104, based on the data set created for the plurality of sensor devices 102 and 104. The learning units 64 and 74 may learn measurement results relating to the movement amount of the 1 st structure 11, the rotation amount of the 1 st structure 11, or the external force applied to the 1 st structure 11, from the data sets created for the plurality of sensor devices 103 and 104.

The learning units 54, 64, and 74 may acquire data sets from a plurality of sensor devices 102, 103, and 104 used at the same site, or may acquire data sets from a plurality of sensor devices 102, 103, and 104 used at different sites. The data set may be a data set collected from a plurality of instruments such as robots that operate independently of each other in a plurality of fields. After the collection of the data set from the plurality of sensor devices 102, 103, 104 is started, a new sensor device 102, 103, 104 may be added to the object of the collection of the data set. In addition, after the collection of the data set from the plurality of sensor devices 102, 103, 104 is started, a part of the plurality of sensor devices 102, 103, 104 may be excluded from the object of collecting the data set.

The learning units 54, 64, and 74, which learn whether or not a detection abnormality or a measurement result is present in any one of the sensor devices 102, 103, and 104, may be mounted on the other sensor devices 102, 103, and 104 than the sensor devices 102, 103, and 104. The learning units 54, 64, and 74 attached to the other sensor devices 102, 103, and 104 can update the output prediction model by relearning in the other sensor devices 102, 103, and 104.

The Learning algorithm used in the Learning units 54, 64, and 74 can use Deep Learning (Deep Learning) for Learning the extraction of the feature amount. The learning sections 54, 64, 74 may perform machine learning according to well-known methods other than deep learning, such as genetic programming, functional logic programming, support vector machines, and the like.

The configurations described in the above embodiments are only examples of the contents of the present invention, and may be combined with other known techniques, and some of the configurations may be omitted or modified without departing from the scope of the present invention.

Description of the reference numerals

11 st structure 1, 12 nd structure, 13 elastic body, 14a, 14b, 14c sensor unit, 15a, 15b, 15c magnetic sensor, 16a, 16b, 16c magnet, 17, 27 communication unit, 20, 28, 50, 60, 70 measuring device, 21 acquisition unit, 22, 51, 61, 71 control unit, 23 storage unit, 24 output unit, 25, 62 arithmetic unit, 26, 52 determination unit, 41 processing circuit, 42 external storage unit, 43 input/output interface, 44 processor, 45 memory, 53, 63, 73 teacher data acquisition unit, 54, 64, 74 learning unit, 55 external magnetic information, 65 external measuring instrument, 100, 101, 102, 103, 104 sensing device, 200 sensing device system.

Claims (8)

1. A sensor device for detecting the movement of an operating body that moves when an external force is applied,

the sensing device is characterized by having:

a 1 st structure which is the operation body;

a 2 nd structure other than the operating body;

a plurality of sensor units each including a magnetic sensor as an element disposed in one of the 1 st and 2 nd structures and a magnet as an element disposed in the other of the 1 st and 2 nd structures, and detecting a change in relative position between the magnetic sensor and the magnet based on a change in magnetic flux detected by the magnetic sensor;

a calculation unit that obtains measurement results regarding at least 1 of a movement amount of the 1 st structure with respect to the 2 nd structure, a rotation amount of the 1 st structure with respect to the 2 nd structure, and the external force applied to the 1 st structure, by calculation based on detection results of the plurality of sensor units; and

and a determination unit that determines, based on detection results of the plurality of sensor units, whether or not there is an abnormality in which the magnetic flux changes due to a factor other than a change in relative position between the magnetic sensor and the magnet.

2. The sensing apparatus of claim 1,

the determination unit determines whether or not the abnormality is present based on a result of obtaining a distance between the plurality of elements arranged in the 1 st structure or a result of obtaining a distance between the plurality of elements arranged in the 2 nd structure.

3. The sensing apparatus of claim 1,

the calculation unit obtains displacement data indicating the movement amount or the rotation amount based on a selected value among values of magnetic fluxes in a plurality of directions obtained by the plurality of magnetic sensors, and obtains the plurality of displacement data by changing a selection pattern of values used for calculation of the displacement data,

the judgment unit judges the presence or absence of the abnormality based on whether or not the plurality of pieces of displacement data match.

4. The sensing apparatus of any one of claims 1 to 3,

the 1 st structure and the 2 nd structure are coupled to each other such that the 1 st structure is movable relative to the 2 nd structure.

5. The sensing apparatus of claim 1,

the number of values as the detection results of the plurality of sensor units is larger than the number of values as the measurement results obtained by the calculation in the calculation unit.

6. The sensing apparatus of claim 1,

a teacher data acquisition unit configured to acquire at least 1 of teacher data of a result obtained by obtaining a distance between the plurality of elements arranged in the 1 st structure and a result obtained by obtaining a distance between the plurality of elements arranged in the 2 nd structure based on information on presence of magnetism outside the sensor device,

the determination unit includes a learning unit that learns whether or not the abnormality is present, based on a data set created based on a combination of the state variables including the detection results obtained by the plurality of sensor units and the teacher data.

7. The sensing apparatus of claim 1,

a teacher data acquisition unit configured to acquire teacher data that is at least 1 of a result of actually measuring the movement amount, a result of actually measuring the rotation amount, and a result of actually measuring the external force,

the calculation unit includes a learning unit that learns measurement results regarding at least 1 of the movement amount, the rotation amount, and the external force, in accordance with a data set created based on a combination of the state variables including the detection results obtained by the plurality of sensor units and the teacher data.

8. A sensor system for detecting the movement of an operating body that moves when an external force is applied,

the sensing device system is characterized by comprising:

a 1 st structure which is the operation body;

a 2 nd structure other than the operating body;

a plurality of sensor units each including a magnetic sensor as an element disposed in one of the 1 st and 2 nd structures and a magnet as an element disposed in the other of the 1 st and 2 nd structures, and detecting a change in relative position between the magnetic sensor and the magnet based on a change in magnetic flux detected by the magnetic sensor;

a calculation unit that obtains measurement results regarding at least 1 of a movement amount of the 1 st structure with respect to the 2 nd structure, a rotation amount of the 1 st structure with respect to the 2 nd structure, and the external force applied to the 1 st structure, by calculation based on detection results of the plurality of sensor units; and

and a determination unit that determines, based on detection results of the plurality of sensor units, whether or not there is an abnormality in which the magnetic flux changes due to a factor other than a change in relative position between the magnetic sensor and the magnet.

Images